A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Transfer Adaptation Learning: A Decade Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
A research problem is characterized as transfer adaptation learning (TAL) when it needs knowledge correspondence between different moments/domains. ...
Broader solutions of transfer adaptation learning being created by researchers are identified, i.e., instance re-weighting adaptation, feature adaptation, classifier adaptation, deep network adaptation ...
ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr. ...
arXiv:1903.04687v2
fatcat:wurprqieffalnnp6isfkhh5y5i
Domain Adaptation for Visual Applications: A Comprehensive Survey
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
After a general motivation, we first position domain adaptation in the larger transfer learning problem. ...
Finally, we conclude the paper with a section where we relate domain adaptation to other machine learning solutions. ...
Domain Adaptation (DA) is a particular case of transfer learning (TL) that leverages labeled data in one or more related source domains, to learn a classifier for unseen or unlabeled data in a target domain ...
arXiv:1702.05374v2
fatcat:5va4oz4evjfhxgxddflpbb6pxi
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
However, the trained model cannot produce a highly discriminative feature representation for the target domain because the training data is dominated by labeled samples from the source domain. ...
Pseudo labeling expands the number of "labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning. ...
Semi-supervised Domain Adaptation Semi-supervised domain adaptation (SSDA) is a relatively promising form of transfer learning, which intents to leverage a small number of labeled samples (e.g, one or ...
arXiv:2104.09415v1
fatcat:lmtocnxxlnd6pahcxgk5oahq7i
Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
A key ingredient of PA-1SmT is to transfer knowledge through adaptive learning of a common model parameter dictionary, which is completely different from existing popular methods for UDA, such as subspace ...
Accordingly, for such a new UDA scenario, we propose a UDA framework through the model parameter adaptation (PA-1SmT). ...
Therefore, we propose a model parameter adaptation framework (PA-1SmT) for this scenario to transfer knowledge through adaptive learning of a common model parameter dictionary, and in turn, use the common ...
arXiv:1809.00852v2
fatcat:loowptfrxngcnel3bvj6qrr5jm
Adaptative Balanced Distribution for Domain Adaptation with Strong Alignment
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
and adding a self-learning network to simultaneously balance them. ...
Aligning and balancing the marginal and conditional feature distributions are two critical procedures for unsupervised domain adaptation (UDA) problems. ...
Therefore, domain adaptation methods based on deep learning have become popular these years. ...
doi:10.1109/access.2021.3096877
fatcat:wjhrcndtgra3tnx3risvcrcz3m
Class-Incremental Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision. ...
Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. ...
under a domain-shift. ...
arXiv:2008.01389v1
fatcat:ukx4f6ohbzgyvo3vo2rvplxjje
Cross domain distribution adaptation via kernel mapping
2009
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
When labeled examples are limited and difficult to obtain, transfer learning employs knowledge from a source domain to improve learning accuracy in the target domain. ...
To solve this problem, we propose an adaptive kernel approach that maps the marginal distribution of targetdomain and source-domain data into a common kernel space, and utilize a sample selection strategy ...
of Computer Science and Engineering at Shanghai Jiao Tong University for sharing the preprocessed Reuters-21578 data set. ...
doi:10.1145/1557019.1557130
dblp:conf/kdd/ZhongFPZRTV09
fatcat:mghl6dcxffbgpmygfl34edg5ay
Class-imbalanced Domain Adaptation: An Empirical Odyssey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Towards a better solution, we further proposed a feature and label distribution CO-ALignment (COAL) model with a novel combination of existing ideas. ...
Unsupervised domain adaptation is a promising way to generalize deep models to novel domains. ...
Domain Adaptation for Label Shift Despite its wide applicability, learning under label shift remains under-explored. ...
arXiv:1910.10320v2
fatcat:muhxzxj74vfc3f6jfqglcetmjq
Generalized Source-free Domain Adaptation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. ...
Some recent works tackle source-free domain adaptation (SFDA) where only a source pre-trained model is available for adaptation to the target domain. ...
Acknowledgement We acknowledge the support from Huawei Kirin Solution, and the project PID2019-104174GB-I00 (MINECO, Spain) and RTI2018-102285-A-I00 (MICINN, Spain), Ramón y Cajal fellowship RYC2019-027020 ...
arXiv:2108.01614v2
fatcat:dixwxo5knneg7bb3g4da4ydonq
DistillAdapt: Source-Free Active Visual Domain Adaptation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The problem requires adapting a pretrained source domain network to a target domain, within a provided budget for acquiring labels in the target domain, while assuming that the source data is not available ...
source data for adaptation. ...
Domain Adaptation Domain adaptation aims to transfer the knowledge learned by a source domain model to an unlabeled target domain. ...
arXiv:2205.12840v1
fatcat:ct2hgy3tlfcvlox7t5pd3ovnl4
Lifelong aspect extraction from big data: knowledge engineering
2016
Complex Adaptive Systems Modeling
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Lifelong learning models are tailored for big data having a knowledge module that is maintained automatically. ...
It includes all supervised, semi-supervised, transfer learning, hybrid and unsupervised techniques having a single target domain known prior to analysis. ...
Acknowledgements We are thankful to Bahria University, Islambad for providing the necessary environment and support to carry out this work. ...
doi:10.1186/s40294-016-0018-7
fatcat:bs5qo3f3lnfb7bwarbvfxxdr2m
Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2003.08051v2 fatcat:4ijpii7j5ffirfmugoyj6wsamuOther Versions
Unsupervised domain adaptation (UDA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to help the learning of unlabeled target domain by transferring knowledge ...
from the source domain. ...
PA-1SmT PA-1SmT [27] was constructed based on the SLMC model by additionally incorporating cross-domain knowledge transferring terms between the source and target domains, under the assumption that the ...
arXiv:2003.08051v3
fatcat:2lqzh2oynrd6xi4cyrximo3xi4
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The scheme first clusters compound target data based on style, discovering multiple latent domains (discover). ...
Finally, target-to-source alignment is learned separately between domains (adapt). In high-level, our solution replaces a hard OCDA problem with much easier multiple UDA problems. ...
Acknowledgements This work was supported by Samsung Electronics Co., Ltd ...
arXiv:2110.04111v1
fatcat:udbcpkspyngvlasaywt5xzczpi
A Survey of Unsupervised Deep Domain Adaptation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As a complement to this challenge, single-source unsupervised domain adaptation can handle situations where a network is trained on labeled data from a source domain and unlabeled data from a related but ...
Deep learning has produced state-of-the-art results for a variety of tasks. ...
Domain Adaptation. One popular type of transfer learning is domain adaptation, which will be the focus of our survey. Domain adaptation is a type of transductive transfer learning. ...
arXiv:1812.02849v3
fatcat:paefg5cywbe3tjsp6dffnwkvxy
Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
2021
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Concretely, we propose a Dynamic and Symmetric Cross Entropy loss (DSCE) to deal with noisy samples and a camera-aware meta-learning algorithm (MetaCam) to adapt camera shift. ...
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. ...
of changes of clusters and thus promotes the model performance. • We propose a camera-aware meta-learning algorithm (MetaCam) for adapting the shifts caused by cameras. ...
doi:10.5281/zenodo.5014558
fatcat:hm4mo4jpandvfk2jfeq2sh26b4
« Previous
Showing results 1 — 15 out of 41,369 results